# Image Classification and Counterfactual Recourse on FASHION-MNIST RECOURSE

Source: [Image Classification and Counterfactual Recourse on FASHION-MNIST RECOURSE](<https://www.sota2.com/research/sota/image-classification-and-counterfactual-recourse-on-fashion-mnist-recourse>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-19T09:33:23.205Z

Evaluation of Image Classification performance and counterfactual recourse quality (VD, CRG, DirSim) using the FASHION-MNIST RECOURSE dataset.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Classification and Counterfactual Recourse |
| Dataset (including any stated split) | FASHION-MNIST RECOURSE |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-and-counterfactual-recourse-on-fashion-mnist-recourse.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [VD](<https://www.sota2.com/research/sota/image-classification-and-counterfactual-recourse-on-fashion-mnist-recourse.md?metric=VD>): Higher is better; unit: SCALAR.

- [CRG](<https://www.sota2.com/research/sota/image-classification-and-counterfactual-recourse-on-fashion-mnist-recourse.md?metric=CRG>): Higher is better; unit: SCALAR.

- [DirSim](<https://www.sota2.com/research/sota/image-classification-and-counterfactual-recourse-on-fashion-mnist-recourse.md?metric=DirSim>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PTQ INT8 | 91.7 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| CFQ-QAT | 91.4 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| CF-PTQ | 91.3 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| MixedPrec-QAT | 91.2 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| KD+Quant | 91 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| PTQ INT4 | 90.1 | Not recorded | 6a0bee90dbc836b87d82c3a9 |
| Prune+Quant | 89.9 | Not recorded | 6a0bee90dbc836b87d82c3a9 |

### PTQ INT8

Accuracy: 91.7. Result ID: 6a0c2e54fbc373592c029ce4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Overhead":"1.00×"}. This record does not assert independent reproduction.

### CFQ-QAT

Accuracy: 91.4. Result ID: 6a0c2e54fbc373592c029cea.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Overhead":"1.41×"}. This record does not assert independent reproduction.

### CF-PTQ

Accuracy: 91.3. Result ID: 6a0c2e54fbc373592c029ce9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Overhead":"1.24×"}. This record does not assert independent reproduction.

### MixedPrec-QAT

Accuracy: 91.2. Result ID: 6a0c2e54fbc373592c029ce6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a41e209131cea0b895.md>)

Recorded evaluation configuration: {"Overhead":"1.15×"}. This record does not assert independent reproduction.

### KD+Quant

Accuracy: 91. Result ID: 6a0c2e54fbc373592c029ce8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61b81e209131ce9f5b87.md>)

Recorded evaluation configuration: {"Overhead":"1.22×"}. This record does not assert independent reproduction.

### PTQ INT4

Accuracy: 90.1. Result ID: 6a0c2e54fbc373592c029ce5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

Recorded evaluation configuration: {"Overhead":"1.00×"}. This record does not assert independent reproduction.

### Prune+Quant

Accuracy: 89.9. Result ID: 6a0c2e54fbc373592c029ce7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0bee90dbc836b87d82c3a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa624a1e209131ce9f8a38.md>)

Recorded evaluation configuration: {"Overhead":"1.10×"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.